iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face Inside the rogue ChatGPT hack of Hugging Face: AI agents operate at superhuman speed but make clumsy mistakes Landstar Expects to Emerge a Winner After Supreme Court’s Montgomery Ruling Widens Broker Liability New Senate bill targets 'chameleon carriers' that reopen to escape penalties Werner Enterprises Posts Highest Revenue Per Truck Growth in One-Way Segment in a Decade CMA CGM and Stonepeak Launch United Ports LLC in $2.4 Billion Terminal Joint Venture UPS shift away from Amazon shows bigger payoff Lanesurf: 62% of Loads Get Vetted Carrier Offers Before Brokers Arrive India-China Border Trade Via Lipulekh Resumes Aug 1; China Permits 20 Traders Geopolitics Drives CMA CGM Q2 Profit Surge of 42% as Volumes and Rates Climb OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face Inside the rogue ChatGPT hack of Hugging Face: AI agents operate at superhuman speed but make clumsy mistakes Landstar Expects to Emerge a Winner After Supreme Court’s Montgomery Ruling Widens Broker Liability New Senate bill targets 'chameleon carriers' that reopen to escape penalties Werner Enterprises Posts Highest Revenue Per Truck Growth in One-Way Segment in a Decade CMA CGM and Stonepeak Launch United Ports LLC in $2.4 Billion Terminal Joint Venture UPS shift away from Amazon shows bigger payoff Lanesurf: 62% of Loads Get Vetted Carrier Offers Before Brokers Arrive India-China Border Trade Via Lipulekh Resumes Aug 1; China Permits 20 Traders Geopolitics Drives CMA CGM Q2 Profit Surge of 42% as Volumes and Rates Climb
Home ›› Technology ›› Ai ›› Ai Ethics ›› New Benchmark Reveals AI Agents Leak Private Data Even When Focused on Tasks

New Benchmark Reveals AI Agents Leak Private Data Even When Focused on Tasks

A new benchmark called TRAP evaluates the trade-off between task accuracy and privacy leakage in AI agents handling sensitive documents. Testing 22 models, the study finds non-trivial privacy leakage across all model families, with instruction-following ability correlating with leakage rate. The authors propose structural private field isolation using hash keys to prevent leakage without sacrificing task performance.

iG
iGEN Editorial
June 21, 2026
New Benchmark Reveals AI Agents Leak Private Data Even When Focused on Tasks

Enterprise AI agents are increasingly deployed in document-intensive workflows—from booking flights using passport numbers to processing customs forms with confidential trade data. In such settings, agents must use private information to complete tasks accurately but must never expose that information in responses, because they cannot verify who is actually at the keyboard. These two obligations are in fundamental tension, according to a paper titled TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction published on arXiv.

The Privacy-Task Accuracy Trade-off

The paper introduces TRAP (Task-completion and Resistance to Active Privacy-extraction), a benchmark designed to evaluate the trade-off between task accuracy and privacy leakage. Each scenario in TRAP includes a document containing private information, a task query that requires the agent to invoke the correct tool using private fields, and an attack query that attempts to elicit the same information in natural language. The authors argue that a model capable enough to use private information for task completion can, by the same capability, be induced to reveal it.

TRAP Benchmark: Evaluation of 22 Models

The study evaluated 22 models spanning frontier proprietary and open-source models at multiple scales. According to the paper, all model families exhibit non-trivial leakage. Furthermore, instruction-following ability correlates with leakage rate—meaning models that are better at following instructions are also more prone to leaking private data when attacked. Existing prompt-based defenses reduce leakage but at a significant cost to task accuracy. The authors found that prompt optimization fails to escape this trade-off.

For any softmax-based model, no soft-constraint defense, e.g., prompt-based defenses, can jointly achieve high task success with zero leakage probability.

This impossibility result, the paper states, is not incidental—it is a fundamental limitation of softmax-based architectures.

Structural Private Field Isolation: A Hard Solution

Motivated by this impossibility, the authors propose structural private field isolation, which replaces private fields with hash keys before they reach the model. This approach largely prevents leakage while keeping task accuracy, according to the paper. By removing raw private data from the model's input, the agent can still use the information via hash-keyed representations without ever exposing the underlying values.

Implications for Enterprise AI in Trade and Logistics

For enterprise decision-makers deploying AI in supply chain, logistics, and trade finance, the TRAP benchmark highlights a critical risk: any AI agent handling sensitive documents—such as invoices, customs declarations, or shipping manifests—may inadvertently leak private data. The finding that instruction-following ability correlates with leakage is particularly concerning for highly capable agents used in automation. The proposed structural isolation approach offers a practical path forward, but it requires modifying how private fields are ingested. Enterprise technology leaders should evaluate whether their AI pipelines incorporate similar safeguards, especially when deploying agents in compliance-heavy, document-driven workflows.

In summary, TRAP provides concrete evidence that privacy leakage is not just a theoretical risk but a measurable property of current AI systems. The benchmark and the proposed defense give CTOs and procurement leaders a framework to assess and mitigate these risks in their own deployments.


Sources:

Keep Reading

Recommended Stories

New StaminaBench Benchmark Reveals Coding Agents Fail After 5-6 Turns Technology

New StaminaBench Benchmark Reveals Coding Agents Fail After 5-6 Turns

Researchers introduce StaminaBench, a benchmark that measures how many consecutive interaction turns coding agents can handle. Testing six harnesses and seven open-source LLMs over 100-turn scenarios, they found all models fail within 5-6 turns. Providing test feedback improved passed turn count by up to 12x, highlighting the importance of iterative testing.

June 22, 2026
TERMS-Bench Diagnoses LLM Negotiation Agents Beyond Deal Rate for Enterprise Procurement Technology

TERMS-Bench Diagnoses LLM Negotiation Agents Beyond Deal Rate for Enterprise Procurement

A new benchmark called TERMS-Bench goes beyond deal rate to diagnose why LLM negotiation agents fail, evaluating 13 frontier models on surplus extraction, cue use, belief calibration, and compliance. For enterprise procurement and trade, this offers actionable insights into AI agent weaknesses.

June 17, 2026
New EEG Benchmark Promises Standardized Evaluation of Foundation Models Technology

New EEG Benchmark Promises Standardized Evaluation of Foundation Models

A new benchmark called EEG-FM-Bench aims to standardize evaluation of electroencephalography foundation models (EEG-FMs). It integrates 14 datasets across 10 paradigms and provides tools for gradient and representation analysis. Early experiments reveal critical insights about multi-task learning, pre-training efficiency, and model scaling.

June 16, 2026
P3B3 Benchmark Reveals Strong Brazilian Portuguese Bias in Large Language Models Technology

P3B3 Benchmark Reveals Strong Brazilian Portuguese Bias in Large Language Models

According to a new research paper, a team introduced P3B3, an expert-curated benchmark for measuring bias between European and Brazilian Portuguese in large language models. Experiments show most LLMs strongly prefer Brazilian Portuguese, underscoring the need for more balanced variety representation in conversational AI.

June 16, 2026